© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 7553
    Prev
    Next
    INDEX
    Explanations

    words related to official processes and forms

    oai_token-act-pair · gemini-2.0-flash

    administrative and procedural terms

    np_token-act-pair-logits · gpt-4o-mini

    Period

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ostavi
    -0.71
    IndentedString
    -0.66
     Wikimedijinoj
    -0.63
     оригіналу
    -0.63
     ویکی‌پدی
    -0.58
    ibatis
    -0.56
     fourrure
    -0.55
     lccn
    -0.55
     Baillargeon
    -0.54
     *)(
    -0.54
    POSITIVE LOGITS
     AssemblyCulture
    0.73
     all
    0.61
     fallu
    0.58
     unknownFields
    0.54
    EndInit
    0.54
     fallait
    0.49
     please
    0.47
    ]--;
    0.47
    __":
    0.46
     email
    0.46
    Activations Density 4.503%

    No Known Activations